ns-execution-gitlab-issue
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitLab issues (titles, descriptions, comments) which creates a vulnerability to indirect prompt injection.
- Ingestion points: Reads GitLab issue payloads using
read_issuevia MCP in Phase 2. - Boundary markers: The instructions do not define specific delimiters or instructions to isolate external text from agent commands.
- Capability inventory: The skill has permission to write files, push to git branches, and modify GitLab issues and Merge Requests.
- Sanitization: No specific text sanitization or verification mechanism is described for external data before it influences agent actions.
Audit Metadata